--- title: dashboards keywords: fastai sidebar: home_sidebar summary: "Supplies dashboards to investigate datasets and training results. Dashboards are defined as classes, to show the dashboard use the .show() function on an dashboard instance." description: "Supplies dashboards to investigate datasets and training results. Dashboards are defined as classes, to show the dashboard use the .show() function on an dashboard instance." nb_path: "nbs/dashboards.ipynb" ---
{% raw %}
{% endraw %} {% raw %}
{% endraw %}

Test data setup

{% raw %} 
import icedata
{% endraw %} {% raw %} 
test_data_dir = icedata.fridge.load_data()
test_class_map = icedata.fridge.class_map()
test_parser = icedata.fridge.parser(test_data_dir)
test_train_records, test_valid_records = test_parser.parse()
test_valid_record_dataset = BboxRecordDataset(test_valid_records, test_class_map)
test_train_record_dataset = BboxRecordDataset(test_train_records, test_class_map)
test_very_large_record_dataset = BboxRecordDataset(test_valid_records*10, test_class_map)
test_record_dataset_no_class_map = BboxRecordDataset(test_train_records)

INFO     - Autofixing records | icevision.parsers.parser:parse:136
{% endraw %} {% raw %} 
import copy
from pathlib import Path
{% endraw %} {% raw %} 
long_record_list = [copy.deepcopy(test_valid_records[0]) for i in range(40_000)]
for index, record in enumerate(long_record_list):
    record.imageid = index
    record.filepath = Path(str("imgs/"+str(index)+".jpg"))
    record.width = np.random.randint(1, 10_000)
long_record_dataset = BboxRecordDataset(long_record_list, test_class_map)
{% endraw %} {% raw %}

class ObjectDetectionDatasetOverview[source]

ObjectDetectionDatasetOverview(dataset:GenericDataset, height:int=500, width:int=500) :: DatasetOverview

Dataset overview for object detection datasets

{% endraw %} {% raw %}
{% endraw %} {% raw %} 
test_object_detection_overview = ObjectDetectionDatasetOverview(test_valid_record_dataset, width=1500, height=900)
test_object_detection_overview.show()
{% endraw %} {% raw %}

class ObjectDetectionDatasetComparison[source]

ObjectDetectionDatasetComparison(datasets:List[GenericDataset], height:int=500, width:int=500) :: DatasetComparison

Dataset comparison for object detection datasets.

{% endraw %} {% raw %}
{% endraw %} {% raw %} 
test_object_detection_comparison = ObjectDetectionDatasetComparison([test_valid_record_dataset, test_train_record_dataset], width=1700, height=700)
test_object_detection_comparison.show()
{% endraw %} {% raw %}

class ObjectDetectionDatasetGeneratorScatter[source]

ObjectDetectionDatasetGeneratorScatter(dataset, with_dataset_overview=False, width=500, height=500) :: DatasetGeneratorScatter

Dataset generator for object detection

{% endraw %} {% raw %}
{% endraw %} {% raw %} 
test_dataset_generator = ObjectDetectionDatasetGeneratorScatter(test_valid_record_dataset, height=700, width=1000)
test_dataset_generator.show()
{% endraw %} {% raw %}

class ObjectDetectionDatasetGeneratorRange[source]

ObjectDetectionDatasetGeneratorRange(dataset, with_dataset_overview=False, width=500, height=500) :: DatasetGenerator

Dataset generator for object detection

{% endraw %} {% raw %}
{% endraw %} {% raw %} 
test_dataset_generator = ObjectDetectionDatasetGeneratorRange(test_valid_record_dataset, height=700, width=1000)
test_dataset_generator.show()
{% endraw %} {% raw %}

class ObjectDetectionResultOverview[source]

ObjectDetectionResultOverview(dataset, plotting_backend='matplotlib', height=700, width=1000) :: Dashboard

Overview dashboard

{% endraw %} {% raw %}
{% endraw %} {% raw %} 
odrd = ObjectDetectionResultsDataset.load("test_data/fridge_train.dat")
odrdash = ObjectDetectionResultOverview(odrd, width=1500)
{% endraw %} {% raw %} 
odrdash.show()
{% endraw %}